Position determination method, device, and system, and computer-readable storage medium

Patent metadata

Field	Value
Publication number	US-12586241-B2
Application number	US-202118004508-A
Country	US
Kind code	B2
Filing date	May 18, 2021
Priority date	Jul 9, 2020
Publication date	Mar 24, 2026
Grant date	Mar 24, 2026

Abstract

This disclosure relates to a position determination method, device, system, and computer-readable storage medium, and relates to the field of computer technologies. The method of the present disclosure includes acquiring laser point cloud data measured at a current position point of a vehicle as reference point cloud data, and acquiring point cloud data corresponding to a preset starting point of the vehicle in a point cloud map as target point cloud data; matching the target point cloud data with the reference point cloud data to determine a transformation matrix between the target point cloud data and the reference point cloud data; and determining coordinate information of the current position point according to coordinate information of the preset starting point and the transformation matrix.

First claim

What is claimed is:

1 . A position determination method, executed by a position determination system, comprising:
scanning at a current position point to obtain laser point cloud data by a lidar device arranged on a vehicle body of a vehicle; and by a position determination device arranged on the vehicle body: acquiring the laser point cloud data as reference point cloud data, and acquiring point cloud data corresponding to a preset starting point of the vehicle in a point cloud map as target point cloud data, wherein a position of the preset starting point is known and before the vehicle enters an automatic driving state, the vehicle is arranged at or near the preset starting point; dividing the target point cloud data into ground target point cloud data and non-ground target point cloud data, and dividing the reference point cloud data into ground reference point cloud data and non-ground reference point cloud data; determining a first transformation matrix according to the ground target point cloud data and the ground reference point cloud data; determining a second transformation matrix according to the first transformation matrix, the non-ground target point cloud data, and the non-ground reference point cloud data; determining coordinate information of the current position point according to coordinate information of the preset starting point, the first transformation matrix and the second transformation matrix to obtain an initial position of the vehicle; transforming preset orientation information corresponding to the preset starting point according to the first transformation matrix to obtain first orientation information, and taking a roll angle value and a pitch angle value in the first orientation information as a current roll angle value and a pitch angle value of the vehicle; and transforming the first orientation information according to the second transformation matrix to obtain second orientation information, and taking a yaw angle value in the second orientation information as a current yaw angle value of the vehicle.

2 . The position determination method according to claim 1 , wherein the determining a first transformation matrix according to the ground target point cloud data and the ground reference point cloud data comprises:
performing a down-sampling processing on the ground reference point cloud data to obtain down-sampled ground reference point cloud data; and matching the ground target point cloud data with the down-sampled ground reference point cloud data to obtain a rotation translation matrix from the ground target point cloud data to the down-sampled ground reference point cloud data as the first transformation matrix.

3 . The position determination method according to claim 1 , wherein the determining a second transformation matrix according to the first transformation matrix, the non-ground target point cloud data, and the non-ground reference point cloud data comprises:
transforming the non-ground target point cloud data according to the first transformation matrix to obtain transformed non-ground target point cloud data; performing a down-sampling processing on the non-ground reference point cloud data to obtain down-sampled non-ground reference point cloud data; and matching the transformed non-ground target point cloud data with the down-sampled non-ground reference point cloud data to obtain a rotation translation matrix from the transformed non-ground target point cloud data to the down-sampled non-ground reference point cloud data as the second transformation matrix.

4 . The position determination method according to claim 1 , wherein the determining coordinate information of the current position point according to coordinate information of the preset starting point and the transformation matrix comprises:
transforming the coordinate information of the preset starting point according to the first transformation matrix to obtain first coordinate information, and taking a z-axis coordinate value in the first coordinate information as a z-axis coordinate value of the current position point; and transforming the first coordinate information according to the second transformation matrix to obtain second coordinate information, and taking an x-axis coordinate value and a y-axis coordinate value in the second coordinate information as an x-axis coordinate value and a y-axis coordinate value of the current position point.

5 . The position determination method according to claim 1 , wherein the acquiring point cloud data corresponding to a preset starting point of the vehicle in a point cloud map as target point cloud data comprises:
acquiring, in the point cloud map, point cloud data centered on the preset starting point and within a range corresponding to a lidar measurement range as the target point cloud data, according to the lidar measurement range corresponding to the reference point cloud data.

6 . A position determination device, comprising:
a processor; and a memory coupled to the processor and storing instructions which, when executed by the processor, cause the processor to: control a lidar device arranged on a vehicle body of a vehicle to scan at a current position point to obtain laser point cloud data; acquire the laser point cloud data as reference point cloud data, and acquire point cloud data corresponding to a preset starting point of the vehicle in a point cloud map as target point cloud data, wherein a position of the preset starting point is known and before the vehicle enters an automatic driving state, the vehicle is arranged at or near the preset starting point; divide the target point cloud data into ground target point cloud data and non-ground target point cloud data, and divide the reference point cloud data into ground reference point cloud data and non-ground reference point cloud data; determine a first transformation matrix according to the ground target point cloud data and the ground reference point cloud data; determine a second transformation matrix according to the first transformation matrix, the non-ground target point cloud data, and the non-ground reference point cloud data; determine coordinate information of the current position point according to coordinate information of the preset starting point, the first transformation matrix and the second transformation matrix to obtain an initial position of the vehicle; transform preset orientation information corresponding to the preset starting point according to the first transformation matrix to obtain first orientation information, and take a roll angle value and a pitch angle value in the first orientation information as a current roll angle value and a pitch angle value of the vehicle; and transform the first orientation information according to the second transformation matrix to obtain second orientation information, and take a yaw angle value in the second orientation information as a current yaw angle value of the vehicle.

7 . A position determination system, comprising: the position determination device according to claim 6 ;
a vehicle body, on which the position determination device is arranged; and a lidar device arranged on the vehicle body and configured to scan at the current position point to obtain the laser point cloud data.

8 . The position determination device according to claim 6 , wherein the determining a first transformation matrix according to the ground target point cloud data and the ground reference point cloud data comprises:
performing a down-sampling processing on the ground reference point cloud data to obtain down-sampled ground reference point cloud data; and matching the ground target point cloud data with the down-sampled ground reference point cloud data

Assignees

• Beijing Jingdong Qianshi Tech Co Ltd

Inventors

• Kong Qi
• Zhang Jinfeng

Classifications

• G01S17/06 Primary

  Systems determining position data of a target · CPC title

• G01S7/4808

  Evaluating distance, position or velocity data · CPC title

• G01S17/931

  of land vehicles · CPC title

• G01S17/89

  for mapping or imaging · CPC title

• G01S17/86

  Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders · CPC title